bert-finetuned-ner

This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0636
• Precision: 0.9343
• Recall: 0.9498
• F1: 0.9420
• Accuracy: 0.9861

Model description

This is a model for Named entity recognition NER

Intended uses & limitations

Open source

Training and evaluation data

The conll2003 dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0757	1.0	1756	0.0638	0.9215	0.9362	0.9288	0.9833
0.0352	2.0	3512	0.0667	0.9360	0.9482	0.9421	0.9858
0.0215	3.0	5268	0.0636	0.9343	0.9498	0.9420	0.9861

Framework versions

• Transformers 4.40.2
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1